feat(translation): add model, config, task, API, and UI for default document language translation

- Add detected_language, default_language_text, default_language_code columns to FileRecord
- Add default_document_language column to UserProfile
- Add DEFAULT_DOCUMENT_LANGUAGE config setting (defaults to "en")
- Create translate_to_default_language Celery task
- Integrate translation trigger into embed_metadata_into_pdf pipeline
- Add /api/files/{id}/translate and /api/files/{id}/translation/default API endpoints
- Add /files/{id}/text/default-language view endpoint
- Update file_view.html with translation sections (default language, on-the-fly)
- Add translation keys to en.json
- Create Alembic migration 036
- Update .env.demo

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-03-16 11:54:13 +00:00
parent ff1fde5e48
commit 3a221a62cd
11 changed files with 697 additions and 1 deletions
+7
View File
@@ -258,6 +258,13 @@ OPENAI_MODEL=gpt-4o-mini
# AZURE_OPENAI_API_VERSION=2024-02-01
# AI_MODEL=gpt-4o # deployment name in Azure
# **Document Translation**
# After processing, documents whose detected language differs from the default
# target language are automatically translated. Only the original and this
# default-language version are persisted; other translations are on-the-fly.
# Users can override this in their profile settings.
# DEFAULT_DOCUMENT_LANGUAGE=en
# Azure Document Intelligence (OCR separate from AI provider above)
# **Email Settings (shared SMTP password reset, verification, and system notifications)**
EMAIL_HOST=smtp.example.com